An Artificial Intelligence Approach to Fatigue Crack Length Estimation from Acoustic Emission Waves in Thin Metallic Plates

Abstract

The acoustic emission (AE) technique has become a well-established method of monitoring structural health over recent years. The sensing and analysis of elastic AE waves, which have involved piezoelectric wafer active sensors (PWAS) and time domain and frequency domain analysis, has proven to be effective in yielding fatigue crack-related information. However, not much research has been performed regarding (i) the correlation between the fatigue crack length and AE signal signatures and (ii) artificial intelligence (AI) methodologies to automate the AE waveform analysis. In this paper, this crack length correlation is investigated along with the development of a novel AE signal analysis technique via AI. A finite element model (FEM) study was first performed to understand the effects of fatigue crack length on the resulting AE waveforms and a fatigue experiment was performed to capture experimental AE waveforms. Finally, this database of experimental AE waveforms was used with a convolutional neural network to build a system capable of performing automated classification and prediction of the length of a fatigue crack that excited respective AE signals. AE signals captured during a fatigue crack growth experiment were found to match closely with the FEM simulations. This novel AI system proved to be effective at predicting the crack length of an AE signal at an accuracy of 98.4%. This novel AI-enabled AE signal analysis technique will provide a crucial step forward in the development of a comprehensive structural health monitoring (SHM) system.

Piezoelectric Materials and Sensors for Structural Health Monitoring: Fundamental Aspects, Current Status, and Future Perspectives

“…Many papers have been published to improve the reliability and accuracy of detection and localization of damages, such as Akaike Information Criterion (AIC) for the accurate estimation of measured differential time of arrival [ 95 ], artificial neural network (ANN) [ 99 ], and theoretical modeling based on the phase velocity analysis [ 100 ]. In the recent years, much more advanced methods were evaluated to determine the type, magnitude, and severity of the impact or defects in the structures [ 101 ]. Garrett et al proposed an artificial intelligence approach to estimate the fatigue crack length in thin metallic plates using acoustic-emission-based SHM [ 101 ].…”

“…In the recent years, much more advanced methods were evaluated to determine the type, magnitude, and severity of the impact or defects in the structures [ 101 ]. Garrett et al proposed an artificial intelligence approach to estimate the fatigue crack length in thin metallic plates using acoustic-emission-based SHM [ 101 ]. Finite element modeling was firstly conducted to establish the simulated frequency spectra of calculated PWAS responses for different fatigue-crack-generated AE signals.…”

“… Flowchart of acoustic emission signal processing from microcrack growth event to the time–frequency intensity plot of Choi–Williams transform [ 101 ]. …”

“…23, x FOR PEER REVIEW 13 of 20 metallic plates using acoustic-emission-based SHM[101]. Finite element modeling was firstly conducted to establish the simulated frequency spectra of calculated PWAS responses for different fatigue-crack-generated AE signals.…”

Application of Data Science in the Sustainable Energy Industry

“…Figure 19 shows the material distortion or singularity will be digitally treated to be a set of numbers, as an example of NLP application. Particularly, the arrangement has a standard AI framework to produce the dataset [35]. With the structural sensors, checking the strain regime of the tower, mainly at positions with stress concentration (distortion or change of geometries etc.…”